System

Abstract

An object of the system according to the embodiment is to predict an indication of an officer in advance and correct a defect of a material.SOLUTION: A system includes a collection part, an analysis part, an indication part, and a correction part. A collection part collects the mail, the statement and the data of decision making of the officer. The analysis unit analyzes the data collected by the collection unit and creates an individual avatar. The pointing out unit causes the avatar created by the analysis unit to analyze the presentation material, and predicts and presents a pointing out. The correction unit corrects the deficiency of the material based on the indication presented by the indication unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technology does not efficiently predict the comments of officials and correct any deficiencies in documents, so there is room for improvement.

[0005] The system according to the embodiment aims to predict in advance what will be pointed out by a manager and correct any deficiencies in documents. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, an analysis unit, a commenting unit, and a correction unit. The collection unit collects data on emails, transcripts, and decision-making from managers. The analysis unit analyzes the data collected by the collection unit and creates individual avatars. The commenting unit uses the avatars created by the analysis unit to analyze presentation materials and predict and present comments. The correction unit corrects deficiencies in the materials based on the comments presented by the commenting unit. [Effects of the Invention]

[0007] The system according to the embodiment can predict the comments of managers in advance and correct any deficiencies in documents. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) A system according to an embodiment of the present invention collects data on executives' emails, transcripts, and decision-making processes and creates personalized AI avatars. This system reflects the executive's characteristics. When a presentation document is uploaded, the system analyzes the content and predicts and presents the executive's likely comments. This allows the executive to correct any deficiencies in the document or prepare questions based on the responses received, allowing the executive to focus on the more important discussions during the actual presentation. Furthermore, the avatar can be used to bounce ideas off the executive as many times as needed, reducing the effort required for pre-planning and revising document reviews. For example, the system collects a wide range of data related to the executive's daily work, including meeting minutes, email exchanges, and decision-making processes. Next, AI creates personalized avatars based on the collected data. The AI ​​analyzes the collected data and generates avatars that reflect the executive's characteristics. For example, it learns the executive's speech tendencies and decision-making patterns and reflects them in the avatar. Furthermore, when a presentation document is uploaded, the avatar analyzes the content and predicts and presents the executive's likely comments. For example, the system may provide suggestions such as "This part needs to be explained more specifically" or "The basis for this data should be made clearer." This allows for document deficiencies to be corrected in advance and questions to be prepared. Furthermore, because participants can bounce ideas off the avatar as many times as they like, it reduces the effort required for adjusting document reviews in advance and revising documents each time. For example, by rehearsing a presentation with the avatar and revising the materials based on the suggestions, it is possible to create more complete documents. This allows participants to focus on more important discussions during the actual presentation. By utilizing an AI avatar that reflects the characteristics of senior executives, the system streamlines the preparation and revision of presentation materials, allowing participants to focus on important discussions. Furthermore, it reduces the effort required for adjusting document reviews in advance and revising documents each time, thereby improving work efficiency.

[0029] An avatar generation system according to an embodiment includes a collection unit, an analysis unit, a commenting unit, and a correction unit. The collection unit collects data on emails, transcripts, and decision-making of executives. The executives' emails include, for example, work-related emails. The transcripts include, for example, meeting minutes and audio recordings. The decision-making data includes, for example, the decision-making process and results. The collection unit can, for example, collect a wide range of data related to the executives' daily work. Examples of such data include daily reports, meeting minutes, and project progress reports. The analysis unit analyzes the data collected by the collection unit and creates individual avatars. The analysis unit analyzes the data using, for example, text mining technology. The analysis unit can also learn executives' speech tendencies and decision-making patterns using natural language processing technology. The analysis unit can also extract executives' characteristics using data mining technology and reflect them in the avatars. The commenting unit allows the avatars created by the analysis unit to analyze presentation materials and predict and present comments. The suggestion unit analyzes the content of the presentation materials using, for example, a machine learning algorithm. The suggestion unit can also predict suggestions using a rule-based system. For example, the suggestion unit may suggest suggestions for the content of the presentation materials, such as "This part needs to be explained more specifically" or "The basis for this data should be clarified." The correction unit corrects deficiencies in the materials based on the suggestions suggested by the suggestion unit. The correction unit can, for example, correct grammar. The correction unit can also add or delete content. Furthermore, the correction unit can rehearse the presentation and revise the materials in response to suggestions. Thus, the avatar generation system according to the embodiment utilizes an AI avatar that reflects the characteristics of a manager, thereby streamlining the preparation and revision of presentation materials and allowing participants to focus on important discussions. Some or all of the above-described processing by the correction unit may be performed using, for example, AI, or without AI. For example, the correction unit can correct the materials using an AI model that receives suggestions suggested by the suggestion unit and outputs corrections to the materials.

[0030] The collection unit can collect a wide range of data related to the manager's daily work. Data related to daily work includes, but is not limited to, daily reports, meeting minutes, and project progress reports. The collection unit can collect a wide range of data related to the manager's daily work. For example, daily reports include records of the manager's daily work. Meeting minutes include records of comments made and decisions made in meetings. Project progress reports include records of the project's progress and achievements. By collecting a wide range of data related to the manager's daily work, the manager's characteristics can be understood in detail. Some or all of the above-mentioned processing in the collection unit can be performed using, for example, AI, or without AI. For example, the collection unit can input data related to the manager's daily work into AI and have the AI ​​collect the data.

[0031] The analysis unit can generate an avatar that reflects the characteristics of the executive based on the collected data. The characteristics of the executive include, but are not limited to, decision-making patterns and communication styles. The analysis unit can generate an avatar that reflects the characteristics of the executive based on the collected data. For example, the analysis unit can analyze data using text mining technology to extract the executive's speech tendencies. The analysis unit can also learn the executive's decision-making patterns using natural language processing technology. Furthermore, the analysis unit can extract the executive's communication style using data mining technology and reflect it in the avatar. By generating an avatar that reflects the executive's characteristics based on the collected data, the avatar can analyze presentation materials on behalf of the executive and predict comments. Some or all of the above-described processing by the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the collected data into AI and have the AI ​​generate the avatar.

[0032] The commenting unit can predict and present comments about the content of the presentation materials. Methods for predicting and presenting comments include, but are not limited to, machine learning algorithms and rule-based systems. The commenting unit can predict and present comments about the content of the presentation materials. For example, the commenting unit can analyze the content of the presentation materials using a machine learning algorithm and predict comments. The commenting unit can also predict comments using a rule-based system. For example, the commenting unit can present comments about the content of the presentation materials, such as "This part needs to be explained more specifically" or "The basis for this data should be clarified." By predicting and presenting comments about the content of the presentation materials, deficiencies in the materials can be corrected in advance and questions can be prepared. Some or all of the above-described processing by the commenting unit can be performed using, for example, AI, or without AI. For example, the commenting unit can input the content of the presentation materials into AI and have the AI ​​predict comments.

[0033] The correction unit can correct deficiencies in the material based on the comments. Methods for correcting deficiencies in the material include, but are not limited to, grammar correction and content addition / deletion. The correction unit can correct deficiencies in the material based on the comments. For example, the correction unit can correct grammar. The correction unit can also add or delete content. Furthermore, the correction unit can rehearse the presentation and revise the material in response to the comments. This allows for correcting deficiencies in the material based on the comments, thereby creating a more complete material. Some or all of the above-described processing in the correction unit may be performed using, for example, AI, or may be performed without AI. For example, the correction unit can revise the material using an AI model that inputs the comments presented by the comment unit and outputs corrections to the material.

[0034] The pointing unit can provide specific examples when presenting the points made. Specific examples include, but are not limited to, past cases and simulation results. The pointing unit can provide specific examples when presenting the points made. For example, the pointing unit can provide suggestions based on past cases. The pointing unit can also provide suggestions based on simulation results. By providing specific examples, the points made are better understood and the materials can be easily revised. Some or all of the above-described processing in the pointing unit can be performed using, or without, AI. For example, the pointing unit can input past cases and simulation results into AI and cause the AI ​​to make suggestions that provide specific examples.

[0035] The correction unit can rehearse a presentation and revise the materials in response to feedback. Presentation rehearsals include, but are not limited to, mock presentations and feedback sessions. The correction unit can, for example, rehearse a presentation and revise the materials in response to feedback. For example, the correction unit can conduct a mock presentation and revise the materials in response to feedback. The correction unit can also conduct a feedback session and revise the materials in response to feedback. In this way, by rehearsing a presentation and revising the materials in response to feedback, it is possible to create more complete materials. Some or all of the above-described processing in the correction unit may be performed using, for example, AI, or may be performed without using AI. For example, the correction unit can input the results of the mock presentation or feedback session into AI and have the AI ​​revise the materials.

[0036] The collection unit can analyze the manager's past work history and select an appropriate data collection method. Examples of past work history include, but are not limited to, project progress reports and daily work reports. The collection unit can, for example, analyze the manager's past work history and select the optimal data collection method. For example, the collection unit prioritizes the selection of a data collection method that the manager has frequently used in the past. The collection unit can also select the most efficient data collection method from the manager's work history. Furthermore, the collection unit can analyze the manager's work history and optimize the timing of data collection. This allows the optimal data collection method to be selected by analyzing the manager's past work history. Some or all of the above-described processing in the collection unit can be performed using, for example, AI, or without AI. For example, the collection unit can input the manager's past work history into AI and have the AI ​​select the data collection method.

[0037] The collection unit may filter data based on the executive's current project or area of ​​interest when collecting data. Examples of current projects and areas of interest include, but are not limited to, project titles and keywords. For example, the collection unit may filter data based on the executive's current project or area of ​​interest when collecting data. For example, the collection unit may prioritize collecting data related to the project the executive is currently working on. The collection unit may also filter and collect relevant data based on the executive's area of ​​interest. Furthermore, the collection unit may selectively collect necessary data based on the executive's current work content. Thus, by filtering data based on the executive's current project or area of ​​interest, highly relevant data can be collected. Some or all of the above-described processing in the collection unit may be performed using, or without, AI. For example, the collection unit may input data on the executive's current project or area of ​​interest into AI and have the AI ​​filter the data.

[0038] The collection unit can select an appropriate collection means depending on the input method of the executive when collecting data. Examples of input methods include, but are not limited to, voice input, text input, and image input. For example, the collection unit can select an appropriate collection means depending on the input method of the executive when collecting data. For example, if the executive prefers voice input, the collection unit can prioritize collecting voice data. Also, if the executive prefers text input, the collection unit can prioritize collecting text data. Furthermore, if the executive frequently uses image data, the collection unit can prioritize collecting image data. This allows for efficient data collection by selecting the optimal collection means depending on the executive's input method. Some or all of the above-described processing in the collection unit can be performed using, for example, AI, or without AI. For example, the collection unit can input data on the executive's input method into AI and have the AI ​​select the collection means.

[0039] The collection unit can prioritize collecting highly relevant data by taking into account the geographical location information of the executives when collecting data. Examples of geographical location information include, but are not limited to, GPS data and address information. For example, the collection unit can prioritize collecting highly relevant data by taking into account the geographical location information of the executives when collecting data. For example, if the executive is in a specific area, the collection unit can prioritize collecting data related to that area. Furthermore, if the executive is on a business trip, the collection unit can prioritize collecting data related to the business trip destination. Furthermore, if the executive is in the office, the collection unit can prioritize collecting data related to the office. Thus, by prioritizing the collection of highly relevant data by taking into account the geographical location information of the executives, data can be collected efficiently. Some or all of the above-described processing by the collection unit can be performed using, or without, AI. For example, the collection unit can input the geographical location information of the executives into AI and have the AI ​​collect data.

[0040] The collection unit can analyze the social media activities of the executives during data collection and collect related data. Social media activities include, but are not limited to, the content of posts, the number of followers, and the number of likes. The collection unit can analyze the social media activities of the executives during data collection and collect related data. For example, the collection unit can collect related data based on information shared by the executives on social media. The collection unit can also analyze the content of the executives' social media activities and collect related data. Furthermore, the collection unit can collect related data by referring to the activities of the executives' friends on social media. In this way, by analyzing the executives' social media activities, related data can be efficiently collected. Some or all of the above-described processing by the collection unit can be performed using, for example, AI, or without AI. For example, the collection unit can input data on the executives' social media activities into AI and have the AI ​​collect the data.

[0041] The collection unit can customize the data collection method by reflecting the manager's past feedback when collecting data. Examples of past feedback include, but are not limited to, survey results and review comments. For example, the collection unit can customize the data collection method by reflecting the manager's past feedback when collecting data. For example, the collection unit adjusts the collection method based on feedback provided by the manager in the past. The collection unit can also adjust the timing of data collection by reflecting the manager's past feedback. Furthermore, the collection unit can select the type of data to collect by referring to the manager's past feedback. This allows for efficient data collection by customizing the collection method by reflecting the manager's past feedback. Some or all of the above-described processing by the collection unit may be performed using, for example, AI, or may be performed without AI. For example, the collection unit can input the manager's past feedback data into AI and have the AI ​​customize the collection method.

[0042] During analysis, the analysis unit can adjust the level of detail of the avatar based on the executive's important decision-making patterns. Important decision-making patterns include, but are not limited to, past decision-making history and decision-making criteria. During analysis, the analysis unit can adjust the level of detail of the avatar based on the executive's important decision-making patterns. For example, the analysis unit adjusts the level of detail of the avatar based on the executive's important decision-making patterns. The analysis unit can also analyze the executive's decision-making patterns and optimize the level of detail of the avatar. Furthermore, the analysis unit can adjust the level of detail of the avatar based on the executive's past decision-making patterns. This allows for efficient avatar generation by adjusting the level of detail of the avatar based on the executive's important decision-making patterns. Some or all of the above-described processing in the analysis unit may be performed using, or without, AI. For example, the analysis unit can input data on the executive's important decision-making patterns into AI and have the AI ​​adjust the level of detail of the avatar.

[0043] The analysis unit can apply different analysis algorithms depending on the manager's job category during analysis. Job categories include, but are not limited to, sales, marketing, and development. The analysis unit can apply different analysis algorithms depending on the manager's job category during analysis. For example, if the manager is performing marketing work, the analysis unit can apply an analysis algorithm specialized for marketing. Furthermore, if the manager is performing financial work, the analysis unit can apply an analysis algorithm specialized for finance. Furthermore, if the manager is performing human resources work, the analysis unit can apply an analysis algorithm specialized for human resources. By applying different analysis algorithms depending on the manager's job category, avatars can be generated efficiently. Some or all of the above-described processing by the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input data on the manager's job category into AI and have the AI ​​apply the analysis algorithm.

[0044] During analysis, the analysis unit can improve the accuracy of the avatar by referring to the manager's past analysis results. Past analysis results include, but are not limited to, past reports and analysis logs. During analysis, the analysis unit can improve the accuracy of the avatar by referring to the manager's past analysis results. For example, the analysis unit improves the accuracy of the avatar based on the manager's past analysis results. The analysis unit can also analyze the manager's past analysis results and optimize the avatar's accuracy. Furthermore, the analysis unit can improve the accuracy of the avatar by referring to the manager's past analysis results. In this way, the avatar's accuracy can be improved by referring to the manager's past analysis results. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data on the manager's past analysis results into AI and have the AI ​​improve the avatar's accuracy.

[0045] During analysis, the analysis unit can determine the priority of avatars based on the work history of the manager. Work history includes, but is not limited to, project progress reports and daily work reports. During analysis, the analysis unit can determine the priority of avatars based on the work history of the manager. For example, the analysis unit determines the priority of avatars based on the work history of the manager. The analysis unit can also analyze the work history of the manager and optimize the priority of avatars. Furthermore, the analysis unit can determine the priority of avatars with reference to the work history of the manager. This allows for efficient generation of avatars by determining the priority of avatars based on the work history of the manager. Some or all of the above-described processing by the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input data on the work history of the manager into AI and have the AI ​​determine the priority of avatars.

[0046] The analysis unit can improve the accuracy of the avatar by referring to literature related to the manager during analysis. Examples of related literature include, but are not limited to, academic papers and technical reports. For example, the analysis unit can improve the accuracy of the avatar by referring to literature related to the manager during analysis. For example, the analysis unit can improve the accuracy of the avatar by referring to literature related to the manager. The analysis unit can also analyze literature related to the manager and optimize the accuracy of the avatar. Furthermore, the analysis unit can improve the accuracy of the avatar by referring to literature related to the manager. Thus, by referring to literature related to the manager, the accuracy of the avatar can be improved. Some or all of the above-described processing in the analysis unit can be performed using, or without, AI. For example, the analysis unit can input data on literature related to the manager into AI and have the AI ​​improve the accuracy of the avatar.

[0047] During analysis, the analysis unit can adjust the avatar's use of technical terms according to the executive's level of expertise. Examples of expertise levels include, but are not limited to, qualifications, years of experience, and past achievements. During analysis, the analysis unit can adjust the avatar's use of technical terms according to the executive's level of expertise. For example, the analysis unit adjusts the avatar's use of technical terms according to the executive's level of expertise. The analysis unit can also analyze the executive's level of expertise and optimize the avatar's use of technical terms. Furthermore, the analysis unit can adjust the avatar's use of technical terms based on the executive's level of expertise. This allows for efficient avatar generation by adjusting the avatar's use of technical terms according to the executive's level of expertise. Some or all of the above-described processing by the analysis unit may be performed using, or without, AI. For example, the analysis unit can input data on the executive's level of expertise into AI and cause the AI ​​to execute a process to adjust the use of technical terms.

[0048] The pointing unit can adjust the level of detail of the pointing based on the importance of the presentation materials when making a point. The importance of the presentation materials includes, but is not limited to, the purpose of the presentation and the importance of the target audience. For example, the pointing unit can adjust the level of detail of the pointing based on the importance of the presentation materials when making a pointing. For example, the pointing unit can provide detailed points for important presentation materials. The pointing unit can also provide simplified points for less important presentation materials. Furthermore, the pointing unit can analyze the importance of the presentation materials and adjust the level of detail of the pointing. By adjusting the level of detail of the pointing based on the importance of the presentation materials, it is possible to make points efficiently. Some or all of the above-described processing by the pointing unit may be performed using, or without, AI. For example, the pointing unit can input data on the importance of the presentation materials into AI and cause the AI ​​to execute a process of adjusting the level of detail of the pointing.

[0049] The pointing unit can apply different pointing algorithms depending on the category of the presentation materials when making a pointing operation. Examples of categories of presentation materials include, but are not limited to, technical presentations, sales presentations, and marketing presentations. For example, the pointing unit can apply different pointing algorithms depending on the category of the presentation materials when making a pointing operation. For example, the pointing unit can apply a marketing-specific pointing algorithm to marketing materials. Furthermore, the pointing unit can also apply a finance-specific pointing algorithm to financial materials. Furthermore, the pointing unit can also apply a human resources-specific pointing algorithm to human resources materials. By applying different pointing algorithms depending on the category of the presentation materials, it is possible to make pointing operations efficiently. Some or all of the above-described processing by the pointing unit can be performed using, for example, AI, or without AI. For example, the pointing unit can input data on the category of the presentation materials into AI and cause the AI ​​to apply the pointing algorithm.

[0050] When making a comment, the commenting unit can improve the accuracy of the comment by referring to the manager's past comments. Past comments include, but are not limited to, past feedback and review comments. When making a comment, the commenting unit can improve the accuracy of the comment by referring to the manager's past comments. For example, the commenting unit improves the accuracy of the comment based on the manager's past comments. The commenting unit can also analyze the manager's past comments and optimize the accuracy of the comment. Furthermore, the commenting unit can improve the accuracy of the comment by referring to the manager's past comments. In this way, the accuracy of the comment can be improved by referring to the manager's past comments. Some or all of the above-mentioned processing in the commenting unit may be performed using, for example, AI, or may be performed without using AI. For example, the commenting unit can input data on the manager's past comments into AI and have the AI ​​improve the accuracy of the comment.

[0051] The pointing unit, when making a point, can determine the priority of the pointing based on the submission date of the presentation materials. The submission date of the presentation materials includes, but is not limited to, for example, a submission deadline or a presentation schedule. The pointing unit, when making a pointing, can determine the priority of the pointing based on the submission date of the presentation materials. For example, the pointing unit can prioritize pointing out presentation materials with an upcoming submission deadline. The pointing unit can also postpone pointing out presentation materials with a distant submission deadline. Furthermore, the pointing unit can analyze the submission date of the presentation materials and optimize the priority of the pointing out. Thus, by determining the priority of the pointing out based on the submission date of the presentation materials, the pointing out can be made efficiently. Some or all of the above-described processing in the pointing unit may be performed using, or without, AI. For example, the pointing unit can input data on the submission date of the presentation materials into AI and cause the AI ​​to execute a process of determining the priority of the pointing out.

[0052] The pointing unit can adjust the order of points made based on the relevance of the presentation materials when making points. The relevance of the presentation materials includes, but is not limited to, the purpose of the presentation and the areas of interest of the audience. The pointing unit can adjust the order of points made based on the relevance of the presentation materials when making points. For example, the pointing unit can prioritize points made to important parts of the presentation materials. The pointing unit can also postpone points made to less relevant parts of the presentation materials. Furthermore, the pointing unit can analyze the relevance of the presentation materials and optimize the order of points made. By adjusting the order of points made based on the relevance of the presentation materials, points can be made efficiently. Some or all of the above-described processing by the pointing unit can be performed using, or without, AI. For example, the pointing unit can input data on the relevance of the presentation materials into AI and cause the AI ​​to execute a process of adjusting the order of points made.

[0053] The suggestion unit can adjust the use of technical terms in the suggestions based on the manager's level of expertise when making suggestions. Examples of the level of expertise include, but are not limited to, qualifications, years of experience, and past achievements. For example, the suggestion unit can adjust the use of technical terms in the suggestions based on the manager's level of expertise when making suggestions. For example, the suggestion unit adjusts the use of technical terms in the suggestions based on the manager's level of expertise. The suggestion unit can also analyze the manager's level of expertise and optimize the use of technical terms in the suggestions. Furthermore, the suggestion unit can adjust the use of technical terms in the suggestions based on the manager's level of expertise. This allows for efficient suggestions by adjusting the use of technical terms in the suggestions based on the manager's level of expertise. Some or all of the above-described processing in the suggestion unit may be performed using, or without, AI. For example, the suggestion unit can input data on the manager's level of expertise into AI and cause the AI ​​to execute a process of adjusting the use of technical terms.

[0054] The correction unit can analyze the manager's past correction history to select the optimal correction method when making corrections. Past correction history includes, but is not limited to, past correction logs and feedback comments. For example, the correction unit can analyze the manager's past correction history to select the optimal correction method when making corrections. For example, the correction unit selects the optimal correction method based on the manager's past correction history. The correction unit can also analyze the manager's past correction history to optimize the correction method. Furthermore, the correction unit can select the correction method by referring to the manager's past correction history. In this way, the optimal correction method can be selected by analyzing the manager's past correction history. Some or all of the above-described processing in the correction unit can be performed using, for example, AI, or without AI. For example, the correction unit can input data on the manager's past correction history into AI and have the AI ​​select the correction method.

[0055] The correction unit can apply different correction algorithms depending on the category of the presentation material during correction. Examples of categories of presentation materials include, but are not limited to, technical presentations, sales presentations, and marketing presentations. For example, the correction unit can apply different correction algorithms depending on the category of the presentation material during correction. For example, the correction unit can apply a correction algorithm specialized for marketing to marketing materials. Furthermore, the correction unit can also apply a correction algorithm specialized for finance to financial materials. Furthermore, the correction unit can also apply a correction algorithm specialized for human resources to human resources materials. By applying different correction algorithms depending on the category of the presentation material, the materials can be efficiently corrected. Some or all of the above-described processing in the correction unit can be performed using, for example, AI, or without AI. For example, the correction unit can input data on the category of the presentation material into AI and have the AI ​​apply the correction algorithm.

[0056] The correction unit can improve the accuracy of the corrections by reflecting the manager's feedback during corrections. Examples of feedback include, but are not limited to, survey results and review comments. For example, the correction unit can improve the accuracy of the corrections by reflecting the manager's feedback during corrections. For example, the correction unit improves the accuracy of the corrections based on the manager's feedback. The correction unit can also analyze the manager's feedback and optimize the accuracy of the corrections. Furthermore, the correction unit can improve the accuracy of the corrections by referring to the manager's feedback. Thus, the accuracy of the corrections can be improved by reflecting the manager's feedback. Some or all of the above-described processing in the correction unit may be performed using, or without, AI. For example, the correction unit can input the manager's feedback data into AI and have the AI ​​improve the accuracy of the corrections.

[0057] The correction unit can take the geographical distribution of the presentation materials into consideration when making corrections. Geographical distribution includes, but is not limited to, regional data and geographical influences. For example, the correction unit can take the geographical distribution of the presentation materials into consideration when making corrections. For example, if the presentation materials relate to a specific region, the correction unit can make corrections specific to that region. Also, if the presentation materials relate to multiple regions, the correction unit can make corrections appropriate for each region. Furthermore, the correction unit can analyze the geographical distribution of the presentation materials and make optimal corrections. This allows the presentation materials to be efficiently corrected by taking the geographical distribution of the presentation materials into consideration. Some or all of the above-described processing by the correction unit can be performed using, for example, AI, or without AI. For example, the correction unit can input data on the geographical distribution of the presentation materials into AI and have the AI ​​execute the correction processing.

[0058] The correction unit can improve the accuracy of the corrections by referring to related literature of the presentation materials during correction. Related literature includes, but is not limited to, academic papers and technical reports, for example. The correction unit can improve the accuracy of the corrections by referring to related literature of the presentation materials during correction. For example, the correction unit can improve the accuracy of the corrections by referring to related literature of the presentation materials. The correction unit can also analyze related literature of the presentation materials and optimize the accuracy of the corrections. Furthermore, the correction unit can improve the accuracy of the corrections by referring to related literature of the presentation materials. In this way, the accuracy of the corrections can be improved by referring to related literature of the presentation materials. Some or all of the above-mentioned processing in the correction unit can be performed using, for example, AI, or can be performed without using AI. For example, the correction unit can input data of related literature of the presentation materials into AI and have the AI ​​improve the accuracy of the corrections.

[0059] The revision unit may take into account the market value of the presentation materials when making revisions. Market value includes, but is not limited to, sales forecasts and market research results. The revision unit may take into account the market value of the presentation materials when making revisions. For example, if the presentation materials have a high market value, the revision unit may make detailed revisions. Alternatively, if the presentation materials have a low market value, the revision unit may make simplified revisions. Furthermore, the revision unit may analyze the market value of the presentation materials and make optimal revisions. This allows the presentation materials to be revised efficiently by taking the market value of the presentation materials into consideration. Some or all of the above-described processing in the revision unit may be performed using, for example, AI, or may be performed without using AI. For example, the revision unit may input data on the market value of the presentation materials into AI and have the AI ​​execute the revision processing.

[0060] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0061] The collection unit can analyze the past work history of executives and prioritize the collection of data related to specific projects. For example, executives can prioritize the collection of data on projects that were successful in the past and identify the factors that led to success in similar projects. They can also collect data on failed projects and take measures to avoid similar failures. Furthermore, they can prioritize the collection of data related to projects that executives are currently working on and support the progress of the projects. In this way, by prioritizing the collection of data related to specific projects based on the executives' past work history, the success rate of projects can be improved.

[0062] When making comments on the content of presentation materials, the commenting unit can improve the accuracy of the comments by referring to past feedback from managers. For example, by analyzing feedback that managers have received in the past and making similar comments, the manager's understanding can be deepened. In addition, the content of the comments can be adjusted based on past feedback, and comments can be made to suit the needs of the manager. Furthermore, by referring to past feedback, the timing of comments can be adjusted, reducing the burden on the manager. In this way, by referring to past feedback from managers, the accuracy of comments can be improved and the burden on the manager can be reduced.

[0063] The collection unit can analyze the social media activities of executives and collect related data. For example, the collection unit can collect related data based on information shared by executives on social media. The collection unit can also analyze the content of the executives' social media activities and collect related data. Furthermore, the collection unit can also collect related data by referring to the activities of the executives' friends on social media. In this way, by analyzing the social media activities of executives, related data can be collected efficiently.

[0064] When providing feedback on the content of presentation materials, the feedback unit can adjust the content of the feedback according to the level of expertise of the executive. For example, if the executive has specialized knowledge, detailed feedback can be provided to deepen the executive's understanding. If the executive does not have specialized knowledge, brief feedback can be provided to reduce the executive's burden. Furthermore, the level of expertise of the executive can be analyzed and the content of the feedback can be optimized. This allows for efficient feedback by adjusting the content of the feedback according to the executive's level of expertise.

[0065] When revising presentation materials, the revision department can analyze the past revision history of the executives and select the optimal revision method. For example, the optimal revision method can be selected based on the past revision history of the executives. The revision method can also be optimized by analyzing the past revision history of the executives. Furthermore, the revision method can also be selected by referring to the past revision history of the executives. In this way, the optimal revision method can be selected by analyzing the past revision history of the executives.

[0066] The processing flow of the first embodiment will be briefly explained below.

[0067] Step 1: The collection department collects data on executive emails, transcripts, and decision-making. Executive emails include work-related emails, and transcripts include meeting minutes and audio recordings. Decision-making data includes the decision-making process and results. The collection department can collect a wide range of data related to executives' daily work, such as daily reports, meeting minutes, and project progress reports. Step 2: The analysis unit analyzes the data collected by the collection unit and creates individual avatars. The analysis unit uses text mining and natural language processing technology to analyze the data and learns the speech tendencies and decision-making patterns of executives. It also uses data mining technology to extract the characteristics of executives and reflect them in the avatars. Step 3: The avatar created by the analysis unit analyzes the presentation materials and predicts and presents suggestions. The suggestion unit uses machine learning algorithms and rule-based systems to analyze the contents of the presentation materials and presents suggestions such as "This part needs to be explained more specifically" or "The basis for this data should be made clearer." Step 4: The correction department corrects any deficiencies in the document based on the suggestions made by the suggestions department. The correction department can correct grammar, add or delete content, rehearse the presentation, and revise the document based on the suggestions. The correction department's processing may be performed using AI or without AI.

[0068] (Example 2) A system according to an embodiment of the present invention collects data on executives' emails, transcripts, and decision-making processes and creates personalized AI avatars. This system reflects the executive's characteristics. When a presentation document is uploaded, the system analyzes the content and predicts and presents the executive's likely comments. This allows the executive to correct any deficiencies in the document or prepare questions based on the responses received, allowing the executive to focus on the more important discussions during the actual presentation. Furthermore, the avatar can be used to bounce ideas off the executive as many times as needed, reducing the effort required for pre-planning and revising document reviews. For example, the system collects a wide range of data related to the executive's daily work, including meeting minutes, email exchanges, and decision-making processes. Next, AI creates personalized avatars based on the collected data. The AI ​​analyzes the collected data and generates avatars that reflect the executive's characteristics. For example, it learns the executive's speech tendencies and decision-making patterns and reflects them in the avatar. Furthermore, when a presentation document is uploaded, the avatar analyzes the content and predicts and presents the executive's likely comments. For example, the system may provide suggestions such as "This part needs to be explained more specifically" or "The basis for this data should be made clearer." This allows for document deficiencies to be corrected in advance and questions to be prepared. Furthermore, because participants can bounce ideas off the avatar as many times as they like, it reduces the effort required for adjusting document reviews in advance and revising documents each time. For example, by rehearsing a presentation with the avatar and revising the materials based on the suggestions, it is possible to create more complete documents. This allows participants to focus on more important discussions during the actual presentation. By utilizing an AI avatar that reflects the characteristics of senior executives, the system streamlines the preparation and revision of presentation materials, allowing participants to focus on important discussions. Furthermore, it reduces the effort required for adjusting document reviews in advance and revising documents each time, thereby improving work efficiency.

[0069] An avatar generation system according to an embodiment includes a collection unit, an analysis unit, a commenting unit, and a correction unit. The collection unit collects data on emails, transcripts, and decision-making of executives. The executives' emails include, for example, work-related emails. The transcripts include, for example, meeting minutes and audio recordings. The decision-making data includes, for example, the decision-making process and results. The collection unit can, for example, collect a wide range of data related to the executives' daily work. Examples of such data include daily reports, meeting minutes, and project progress reports. The analysis unit analyzes the data collected by the collection unit and creates individual avatars. The analysis unit analyzes the data using, for example, text mining technology. The analysis unit can also learn executives' speech tendencies and decision-making patterns using natural language processing technology. The analysis unit can also extract executives' characteristics using data mining technology and reflect them in the avatars. The commenting unit allows the avatars created by the analysis unit to analyze presentation materials and predict and present comments. The suggestion unit analyzes the content of the presentation materials using, for example, a machine learning algorithm. The suggestion unit can also predict suggestions using a rule-based system. For example, the suggestion unit may suggest suggestions for the content of the presentation materials, such as "This part needs to be explained more specifically" or "The basis for this data should be clarified." The correction unit corrects deficiencies in the materials based on the suggestions suggested by the suggestion unit. The correction unit can, for example, correct grammar. The correction unit can also add or delete content. Furthermore, the correction unit can rehearse the presentation and revise the materials in response to suggestions. Thus, the avatar generation system according to the embodiment utilizes an AI avatar that reflects the characteristics of a manager, thereby streamlining the preparation and revision of presentation materials and allowing participants to focus on important discussions. Some or all of the above-described processing by the correction unit may be performed using, for example, AI, or without AI. For example, the correction unit can correct the materials using an AI model that receives suggestions suggested by the suggestion unit and outputs corrections to the materials.

[0070] The collection unit can collect a wide range of data related to the manager's daily work. Data related to daily work includes, but is not limited to, daily reports, meeting minutes, and project progress reports. The collection unit can collect a wide range of data related to the manager's daily work. For example, daily reports include records of the manager's daily work. Meeting minutes include records of comments made and decisions made in meetings. Project progress reports include records of the project's progress and achievements. By collecting a wide range of data related to the manager's daily work, the manager's characteristics can be understood in detail. Some or all of the above-mentioned processing in the collection unit can be performed using, for example, AI, or without AI. For example, the collection unit can input data related to the manager's daily work into AI and have the AI ​​collect the data.

[0071] The analysis unit can generate an avatar that reflects the characteristics of the executive based on the collected data. The characteristics of the executive include, but are not limited to, decision-making patterns and communication styles. The analysis unit can generate an avatar that reflects the characteristics of the executive based on the collected data. For example, the analysis unit can analyze data using text mining technology to extract the executive's speech tendencies. The analysis unit can also learn the executive's decision-making patterns using natural language processing technology. Furthermore, the analysis unit can extract the executive's communication style using data mining technology and reflect it in the avatar. By generating an avatar that reflects the executive's characteristics based on the collected data, the avatar can analyze presentation materials on behalf of the executive and predict comments. Some or all of the above-described processing by the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the collected data into AI and have the AI ​​generate the avatar.

[0072] The commenting unit can predict and present comments about the content of the presentation materials. Methods for predicting and presenting comments include, but are not limited to, machine learning algorithms and rule-based systems. The commenting unit can predict and present comments about the content of the presentation materials. For example, the commenting unit can analyze the content of the presentation materials using a machine learning algorithm and predict comments. The commenting unit can also predict comments using a rule-based system. For example, the commenting unit can present comments about the content of the presentation materials, such as "This part needs to be explained more specifically" or "The basis for this data should be clarified." By predicting and presenting comments about the content of the presentation materials, deficiencies in the materials can be corrected in advance and questions can be prepared. Some or all of the above-described processing by the commenting unit can be performed using, for example, AI, or without AI. For example, the commenting unit can input the content of the presentation materials into AI and have the AI ​​predict comments.

[0073] The correction unit can correct deficiencies in the material based on the comments. Methods for correcting deficiencies in the material include, but are not limited to, grammar correction and content addition / deletion. The correction unit can correct deficiencies in the material based on the comments. For example, the correction unit can correct grammar. The correction unit can also add or delete content. Furthermore, the correction unit can rehearse the presentation and revise the material in response to the comments. This allows for correcting deficiencies in the material based on the comments, thereby creating a more complete material. Some or all of the above-described processing in the correction unit may be performed using, for example, AI, or may be performed without AI. For example, the correction unit can revise the material using an AI model that inputs the comments presented by the comment unit and outputs corrections to the material.

[0074] The pointing unit can provide specific examples when presenting the points made. Specific examples include, but are not limited to, past cases and simulation results. The pointing unit can provide specific examples when presenting the points made. For example, the pointing unit can provide suggestions based on past cases. The pointing unit can also provide suggestions based on simulation results. By providing specific examples, the points made are better understood and the materials can be easily revised. Some or all of the above-described processing in the pointing unit can be performed using, or without, AI. For example, the pointing unit can input past cases and simulation results into AI and cause the AI ​​to make suggestions that provide specific examples.

[0075] The correction unit can rehearse a presentation and revise the materials in response to feedback. Presentation rehearsals include, but are not limited to, mock presentations and feedback sessions. The correction unit can, for example, rehearse a presentation and revise the materials in response to feedback. For example, the correction unit can conduct a mock presentation and revise the materials in response to feedback. The correction unit can also conduct a feedback session and revise the materials in response to feedback. In this way, by rehearsing a presentation and revising the materials in response to feedback, it is possible to create more complete materials. Some or all of the above-described processing in the correction unit may be performed using, for example, AI, or may be performed without using AI. For example, the correction unit can input the results of the mock presentation or feedback session into AI and have the AI ​​revise the materials.

[0076] The collection unit can estimate the user's emotions and determine the timing of data collection based on the estimated user emotions. The collection unit can, for example, estimate the user's emotions and adjust the timing of data collection based on the estimated user emotions. For example, if the user is feeling stressed, the collection unit can reduce the frequency of data collection to reduce the burden. Also, if the user is relaxed, the collection unit can increase the frequency of data collection to collect more detailed data. Also, if the user is busy, the collection unit can adjust the timing of data collection to between work tasks. In this way, by adjusting the timing of data collection according to the user's emotions, the burden on the user can be reduced. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processing in the collection unit can be performed using, for example, an AI. For example, the collection unit can input the user's emotion data into an AI and cause the AI ​​to execute a process of adjusting the timing of data collection.

[0077] The collection unit can analyze the manager's past work history and select an appropriate data collection method. Examples of past work history include, but are not limited to, project progress reports and daily work reports. The collection unit can, for example, analyze the manager's past work history and select the optimal data collection method. For example, the collection unit prioritizes the selection of a data collection method that the manager has frequently used in the past. The collection unit can also select the most efficient data collection method from the manager's work history. Furthermore, the collection unit can analyze the manager's work history and optimize the timing of data collection. This allows the optimal data collection method to be selected by analyzing the manager's past work history. Some or all of the above-described processing in the collection unit can be performed using, for example, AI, or without AI. For example, the collection unit can input the manager's past work history into AI and have the AI ​​select the data collection method.

[0078] The collection unit may filter data based on the executive's current project or area of ​​interest when collecting data. Examples of current projects and areas of interest include, but are not limited to, project titles and keywords. For example, the collection unit may filter data based on the executive's current project or area of ​​interest when collecting data. For example, the collection unit may prioritize collecting data related to the project the executive is currently working on. The collection unit may also filter and collect relevant data based on the executive's area of ​​interest. Furthermore, the collection unit may selectively collect necessary data based on the executive's current work content. Thus, by filtering data based on the executive's current project or area of ​​interest, highly relevant data can be collected. Some or all of the above-described processing in the collection unit may be performed using, or without, AI. For example, the collection unit may input data on the executive's current project or area of ​​interest into AI and have the AI ​​filter the data.

[0079] The collection unit can select an appropriate collection means depending on the input method of the executive when collecting data. Examples of input methods include, but are not limited to, voice input, text input, and image input. For example, the collection unit can select an appropriate collection means depending on the input method of the executive when collecting data. For example, if the executive prefers voice input, the collection unit can prioritize collecting voice data. Also, if the executive prefers text input, the collection unit can prioritize collecting text data. Furthermore, if the executive frequently uses image data, the collection unit can prioritize collecting image data. This allows for efficient data collection by selecting the optimal collection means depending on the executive's input method. Some or all of the above-described processing in the collection unit can be performed using, for example, AI, or without AI. For example, the collection unit can input data on the executive's input method into AI and have the AI ​​select the collection means.

[0080] The collection unit can estimate the user's emotions and prioritize the data to be collected based on the estimated user emotions. The collection unit can, for example, estimate the user's emotions and determine the priority of the data to be collected based on the estimated user emotions. For example, if the user is feeling stressed, the collection unit postpones the collection of less important data. Furthermore, if the user is relaxed, the collection unit can prioritize the collection of detailed data. Furthermore, if the user is in a hurry, the collection unit can prioritize the collection of more important data. This allows efficient data collection by determining the priority of the data to be collected according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the collection unit can be performed using, for example, an AI, or without an AI. For example, the collection unit can input the user's emotion data into an AI and cause the AI ​​to perform a process of determining the priority of the data.

[0081] The collection unit can prioritize collecting highly relevant data by taking into account the geographical location information of the executives when collecting data. Examples of geographical location information include, but are not limited to, GPS data and address information. For example, the collection unit can prioritize collecting highly relevant data by taking into account the geographical location information of the executives when collecting data. For example, if the executive is in a specific area, the collection unit can prioritize collecting data related to that area. Furthermore, if the executive is on a business trip, the collection unit can prioritize collecting data related to the business trip destination. Furthermore, if the executive is in the office, the collection unit can prioritize collecting data related to the office. Thus, by prioritizing the collection of highly relevant data by taking into account the geographical location information of the executives, data can be collected efficiently. Some or all of the above-described processing by the collection unit can be performed using, or without, AI. For example, the collection unit can input the geographical location information of the executives into AI and have the AI ​​collect data.

[0082] The collection unit can analyze the social media activities of the executives during data collection and collect related data. Social media activities include, but are not limited to, the content of posts, the number of followers, and the number of likes. The collection unit can analyze the social media activities of the executives during data collection and collect related data. For example, the collection unit can collect related data based on information shared by the executives on social media. The collection unit can also analyze the content of the executives' social media activities and collect related data. Furthermore, the collection unit can collect related data by referring to the activities of the executives' friends on social media. In this way, by analyzing the executives' social media activities, related data can be efficiently collected. Some or all of the above-described processing by the collection unit can be performed using, for example, AI, or without AI. For example, the collection unit can input data on the executives' social media activities into AI and have the AI ​​collect the data.

[0083] The collection unit can customize the data collection method by reflecting the manager's past feedback when collecting data. Examples of past feedback include, but are not limited to, survey results and review comments. For example, the collection unit can customize the data collection method by reflecting the manager's past feedback when collecting data. For example, the collection unit adjusts the collection method based on feedback provided by the manager in the past. The collection unit can also adjust the timing of data collection by reflecting the manager's past feedback. Furthermore, the collection unit can select the type of data to collect by referring to the manager's past feedback. This allows for efficient data collection by customizing the collection method by reflecting the manager's past feedback. Some or all of the above-described processing by the collection unit may be performed using, for example, AI, or may be performed without AI. For example, the collection unit can input the manager's past feedback data into AI and have the AI ​​customize the collection method.

[0084] The analysis unit can estimate the user's emotion and set an avatar generation method based on the estimated user emotion. The analysis unit can, for example, estimate the user's emotion and adjust the avatar generation method based on the estimated user emotion. For example, the analysis unit can generate a detailed avatar if the user is relaxed. The analysis unit can also generate a simplified avatar if the user is in a hurry. The analysis unit can also generate a visually stimulating avatar if the user is excited. This allows for efficient avatar generation by adjusting the avatar generation method according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input user emotion data into AI and have the AI ​​adjust the avatar generation method.

[0085] During analysis, the analysis unit can adjust the level of detail of the avatar based on the executive's important decision-making patterns. Important decision-making patterns include, but are not limited to, past decision-making history and decision-making criteria. During analysis, the analysis unit can adjust the level of detail of the avatar based on the executive's important decision-making patterns. For example, the analysis unit adjusts the level of detail of the avatar based on the executive's important decision-making patterns. The analysis unit can also analyze the executive's decision-making patterns and optimize the level of detail of the avatar. Furthermore, the analysis unit can adjust the level of detail of the avatar based on the executive's past decision-making patterns. This allows for efficient avatar generation by adjusting the level of detail of the avatar based on the executive's important decision-making patterns. Some or all of the above-described processing in the analysis unit may be performed using, or without, AI. For example, the analysis unit can input data on the executive's important decision-making patterns into AI and have the AI ​​adjust the level of detail of the avatar.

[0086] The analysis unit can apply different analysis algorithms depending on the manager's job category during analysis. Job categories include, but are not limited to, sales, marketing, and development. The analysis unit can apply different analysis algorithms depending on the manager's job category during analysis. For example, if the manager is performing marketing work, the analysis unit can apply an analysis algorithm specialized for marketing. Furthermore, if the manager is performing financial work, the analysis unit can apply an analysis algorithm specialized for finance. Furthermore, if the manager is performing human resources work, the analysis unit can apply an analysis algorithm specialized for human resources. By applying different analysis algorithms depending on the manager's job category, avatars can be generated efficiently. Some or all of the above-described processing by the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input data on the manager's job category into AI and have the AI ​​apply the analysis algorithm.

[0087] During analysis, the analysis unit can improve the accuracy of the avatar by referring to the manager's past analysis results. Past analysis results include, but are not limited to, past reports and analysis logs. During analysis, the analysis unit can improve the accuracy of the avatar by referring to the manager's past analysis results. For example, the analysis unit improves the accuracy of the avatar based on the manager's past analysis results. The analysis unit can also analyze the manager's past analysis results and optimize the avatar's accuracy. Furthermore, the analysis unit can improve the accuracy of the avatar by referring to the manager's past analysis results. In this way, the avatar's accuracy can be improved by referring to the manager's past analysis results. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data on the manager's past analysis results into AI and have the AI ​​improve the avatar's accuracy.

[0088] The analysis unit can estimate the user's emotion and set the avatar generation speed based on the estimated user emotion. The analysis unit can, for example, estimate the user's emotion and adjust the avatar generation speed based on the estimated user emotion. For example, the analysis unit can increase the avatar generation speed when the user is in a hurry. The analysis unit can also slow the avatar generation speed when the user is relaxed. The analysis unit can also adjust the avatar generation speed when the user is excited. This allows for efficient avatar generation by adjusting the avatar generation speed according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, an AI. For example, the analysis unit can input the user's emotion data into an AI and have the AI ​​adjust the avatar generation speed.

[0089] During analysis, the analysis unit can determine the priority of avatars based on the work history of the manager. Work history includes, but is not limited to, project progress reports and daily work reports. During analysis, the analysis unit can determine the priority of avatars based on the work history of the manager. For example, the analysis unit determines the priority of avatars based on the work history of the manager. The analysis unit can also analyze the work history of the manager and optimize the priority of avatars. Furthermore, the analysis unit can determine the priority of avatars with reference to the work history of the manager. This allows for efficient generation of avatars by determining the priority of avatars based on the work history of the manager. Some or all of the above-described processing by the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input data on the work history of the manager into AI and have the AI ​​determine the priority of avatars.

[0090] The analysis unit can improve the accuracy of the avatar by referring to literature related to the manager during analysis. Examples of related literature include, but are not limited to, academic papers and technical reports. For example, the analysis unit can improve the accuracy of the avatar by referring to literature related to the manager during analysis. For example, the analysis unit can improve the accuracy of the avatar by referring to literature related to the manager. The analysis unit can also analyze literature related to the manager and optimize the accuracy of the avatar. Furthermore, the analysis unit can improve the accuracy of the avatar by referring to literature related to the manager. Thus, by referring to literature related to the manager, the accuracy of the avatar can be improved. Some or all of the above-described processing in the analysis unit can be performed using, or without, AI. For example, the analysis unit can input data on literature related to the manager into AI and have the AI ​​improve the accuracy of the avatar.

[0091] During analysis, the analysis unit can adjust the avatar's use of technical terms according to the executive's level of expertise. Examples of expertise levels include, but are not limited to, qualifications, years of experience, and past achievements. During analysis, the analysis unit can adjust the avatar's use of technical terms according to the executive's level of expertise. For example, the analysis unit adjusts the avatar's use of technical terms according to the executive's level of expertise. The analysis unit can also analyze the executive's level of expertise and optimize the avatar's use of technical terms. Furthermore, the analysis unit can adjust the avatar's use of technical terms based on the executive's level of expertise. This allows for efficient avatar generation by adjusting the avatar's use of technical terms according to the executive's level of expertise. Some or all of the above-described processing by the analysis unit may be performed using, or without, AI. For example, the analysis unit can input data on the executive's level of expertise into AI and cause the AI ​​to execute a process to adjust the use of technical terms.

[0092] The suggestion unit can estimate the user's emotions and set a method for expressing suggestions based on the estimated user emotions. The suggestion unit can, for example, estimate the user's emotions and adjust the method for expressing suggestions based on the estimated user emotions. For example, if the user is nervous, the suggestion unit can give gentle suggestions. If the user is relaxed, the suggestion unit can give detailed suggestions. If the user is in a hurry, the suggestion unit can give concise suggestions. This allows for efficient suggestions by adjusting the method for expressing suggestions according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the suggestion unit may be performed using an AI, or may be performed without using an AI. For example, the suggestion unit can input user emotion data into an AI and cause the AI ​​to execute a process for adjusting the method for expressing suggestions.

[0093] The pointing unit can adjust the level of detail of the pointing based on the importance of the presentation materials when making a point. The importance of the presentation materials includes, but is not limited to, the purpose of the presentation and the importance of the target audience. For example, the pointing unit can adjust the level of detail of the pointing based on the importance of the presentation materials when making a pointing. For example, the pointing unit can provide detailed points for important presentation materials. The pointing unit can also provide simplified points for less important presentation materials. Furthermore, the pointing unit can analyze the importance of the presentation materials and adjust the level of detail of the pointing. By adjusting the level of detail of the pointing based on the importance of the presentation materials, it is possible to make points efficiently. Some or all of the above-described processing by the pointing unit may be performed using, or without, AI. For example, the pointing unit can input data on the importance of the presentation materials into AI and cause the AI ​​to execute a process of adjusting the level of detail of the pointing.

[0094] The pointing unit can apply different pointing algorithms depending on the category of the presentation materials when making a pointing operation. Examples of categories of presentation materials include, but are not limited to, technical presentations, sales presentations, and marketing presentations. For example, the pointing unit can apply different pointing algorithms depending on the category of the presentation materials when making a pointing operation. For example, the pointing unit can apply a marketing-specific pointing algorithm to marketing materials. Furthermore, the pointing unit can also apply a finance-specific pointing algorithm to financial materials. Furthermore, the pointing unit can also apply a human resources-specific pointing algorithm to human resources materials. By applying different pointing algorithms depending on the category of the presentation materials, it is possible to make pointing operations efficiently. Some or all of the above-described processing by the pointing unit can be performed using, for example, AI, or without AI. For example, the pointing unit can input data on the category of the presentation materials into AI and cause the AI ​​to apply the pointing algorithm.

[0095] When making a comment, the commenting unit can improve the accuracy of the comment by referring to the manager's past comments. Past comments include, but are not limited to, past feedback and review comments. When making a comment, the commenting unit can improve the accuracy of the comment by referring to the manager's past comments. For example, the commenting unit improves the accuracy of the comment based on the manager's past comments. The commenting unit can also analyze the manager's past comments and optimize the accuracy of the comment. Furthermore, the commenting unit can improve the accuracy of the comment by referring to the manager's past comments. In this way, the accuracy of the comment can be improved by referring to the manager's past comments. Some or all of the above-mentioned processing in the commenting unit may be performed using, for example, AI, or may be performed without using AI. For example, the commenting unit can input data on the manager's past comments into AI and have the AI ​​improve the accuracy of the comment.

[0096] The suggestion unit can estimate the user's emotion and set the length of the suggestion based on the estimated user's emotion. The suggestion unit can, for example, estimate the user's emotion and adjust the length of the suggestion based on the estimated user's emotion. For example, if the user is in a hurry, the suggestion unit can provide short, to-the-point suggestions. If the user is relaxed, the suggestion unit can provide detailed suggestions. If the user is nervous, the suggestion unit can provide shorter suggestions in gentler terms. This allows for efficient suggestion by adjusting the length of the suggestion according to the user's emotion. The suggestion of emotion is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the suggestion unit can be performed using, for example, an AI. For example, the suggestion unit can input the user's emotion data into an AI and cause the AI ​​to execute a process of adjusting the length of the suggestion.

[0097] The pointing unit, when making a point, can determine the priority of the pointing based on the submission date of the presentation materials. The submission date of the presentation materials includes, but is not limited to, for example, a submission deadline or a presentation schedule. The pointing unit, when making a pointing, can determine the priority of the pointing based on the submission date of the presentation materials. For example, the pointing unit can prioritize pointing out presentation materials with an upcoming submission deadline. The pointing unit can also postpone pointing out presentation materials with a distant submission deadline. Furthermore, the pointing unit can analyze the submission date of the presentation materials and optimize the priority of the pointing out. Thus, by determining the priority of the pointing out based on the submission date of the presentation materials, the pointing out can be made efficiently. Some or all of the above-described processing in the pointing unit may be performed using, or without, AI. For example, the pointing unit can input data on the submission date of the presentation materials into AI and cause the AI ​​to execute a process of determining the priority of the pointing out.

[0098] The pointing unit can adjust the order of points made based on the relevance of the presentation materials when making points. The relevance of the presentation materials includes, but is not limited to, the purpose of the presentation and the areas of interest of the audience. The pointing unit can adjust the order of points made based on the relevance of the presentation materials when making points. For example, the pointing unit can prioritize points made to important parts of the presentation materials. The pointing unit can also postpone points made to less relevant parts of the presentation materials. Furthermore, the pointing unit can analyze the relevance of the presentation materials and optimize the order of points made. By adjusting the order of points made based on the relevance of the presentation materials, points can be made efficiently. Some or all of the above-described processing by the pointing unit can be performed using, or without, AI. For example, the pointing unit can input data on the relevance of the presentation materials into AI and cause the AI ​​to execute a process of adjusting the order of points made.

[0099] The suggestion unit can adjust the use of technical terms in the suggestions based on the manager's level of expertise when making suggestions. Examples of the level of expertise include, but are not limited to, qualifications, years of experience, and past achievements. For example, the suggestion unit can adjust the use of technical terms in the suggestions based on the manager's level of expertise when making suggestions. For example, the suggestion unit adjusts the use of technical terms in the suggestions based on the manager's level of expertise. The suggestion unit can also analyze the manager's level of expertise and optimize the use of technical terms in the suggestions. Furthermore, the suggestion unit can adjust the use of technical terms in the suggestions based on the manager's level of expertise. This allows for efficient suggestions by adjusting the use of technical terms in the suggestions based on the manager's level of expertise. Some or all of the above-described processing in the suggestion unit may be performed using, or without, AI. For example, the suggestion unit can input data on the manager's level of expertise into AI and cause the AI ​​to execute a process of adjusting the use of technical terms.

[0100] The correction unit can estimate the user's emotions and set a method for correcting the material based on the estimated user emotions. The correction unit can, for example, estimate the user's emotions and adjust the method for correcting the material based on the estimated user emotions. For example, the correction unit can suggest a simple correction method if the user is stressed. The correction unit can also suggest a detailed correction method if the user is relaxed. The correction unit can also suggest a quick correction method if the user is in a hurry. This allows the material to be efficiently corrected by adjusting the method for correcting the material according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the correction unit can be performed using an AI, for example, or without an AI. For example, the correction unit can input the user's emotion data into an AI and cause the AI ​​to execute a process for adjusting the method for correcting the material.

[0101] The correction unit can analyze the manager's past correction history to select the optimal correction method when making corrections. Past correction history includes, but is not limited to, past correction logs and feedback comments. For example, the correction unit can analyze the manager's past correction history to select the optimal correction method when making corrections. For example, the correction unit selects the optimal correction method based on the manager's past correction history. The correction unit can also analyze the manager's past correction history to optimize the correction method. Furthermore, the correction unit can select the correction method by referring to the manager's past correction history. In this way, the optimal correction method can be selected by analyzing the manager's past correction history. Some or all of the above-described processing in the correction unit can be performed using, for example, AI, or without AI. For example, the correction unit can input data on the manager's past correction history into AI and have the AI ​​select the correction method.

[0102] The correction unit can apply different correction algorithms depending on the category of the presentation material during correction. Examples of categories of presentation materials include, but are not limited to, technical presentations, sales presentations, and marketing presentations. For example, the correction unit can apply different correction algorithms depending on the category of the presentation material during correction. For example, the correction unit can apply a correction algorithm specialized for marketing to marketing materials. Furthermore, the correction unit can also apply a correction algorithm specialized for finance to financial materials. Furthermore, the correction unit can also apply a correction algorithm specialized for human resources to human resources materials. By applying different correction algorithms depending on the category of the presentation material, the materials can be efficiently corrected. Some or all of the above-described processing in the correction unit can be performed using, for example, AI, or without AI. For example, the correction unit can input data on the category of the presentation material into AI and have the AI ​​apply the correction algorithm.

[0103] The correction unit can improve the accuracy of the corrections by reflecting the manager's feedback during corrections. Examples of feedback include, but are not limited to, survey results and review comments. For example, the correction unit can improve the accuracy of the corrections by reflecting the manager's feedback during corrections. For example, the correction unit improves the accuracy of the corrections based on the manager's feedback. The correction unit can also analyze the manager's feedback and optimize the accuracy of the corrections. Furthermore, the correction unit can improve the accuracy of the corrections by referring to the manager's feedback. Thus, the accuracy of the corrections can be improved by reflecting the manager's feedback. Some or all of the above-described processing in the correction unit may be performed using, or without, AI. For example, the correction unit can input the manager's feedback data into AI and have the AI ​​improve the accuracy of the corrections.

[0104] The correction unit can estimate the user's emotions and set the priority of corrections based on the estimated user emotions. The correction unit can, for example, estimate the user's emotions and determine the priority of corrections based on the estimated user emotions. For example, if the user is in a hurry, the correction unit can prioritize important corrections. Also, if the user is relaxed, the correction unit can prioritize detailed corrections. Also, if the user is stressed, the correction unit can prioritize simple corrections. This allows for efficient correction of materials by determining the priority of corrections according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the correction unit can be performed using an AI, for example, or without an AI. For example, the correction unit can input the user's emotion data into an AI and cause the AI ​​to execute a process of determining the priority of corrections.

[0105] The correction unit can take the geographical distribution of the presentation materials into consideration when making corrections. Geographical distribution includes, but is not limited to, regional data and geographical influences. For example, the correction unit can take the geographical distribution of the presentation materials into consideration when making corrections. For example, if the presentation materials relate to a specific region, the correction unit can make corrections specific to that region. Also, if the presentation materials relate to multiple regions, the correction unit can make corrections appropriate for each region. Furthermore, the correction unit can analyze the geographical distribution of the presentation materials and make optimal corrections. This allows the presentation materials to be efficiently corrected by taking the geographical distribution of the presentation materials into consideration. Some or all of the above-described processing by the correction unit can be performed using, for example, AI, or without AI. For example, the correction unit can input data on the geographical distribution of the presentation materials into AI and have the AI ​​execute the correction processing.

[0106] The correction unit can improve the accuracy of the corrections by referring to related literature of the presentation materials during correction. Related literature includes, but is not limited to, academic papers and technical reports, for example. The correction unit can improve the accuracy of the corrections by referring to related literature of the presentation materials during correction. For example, the correction unit can improve the accuracy of the corrections by referring to related literature of the presentation materials. The correction unit can also analyze related literature of the presentation materials and optimize the accuracy of the corrections. Furthermore, the correction unit can improve the accuracy of the corrections by referring to related literature of the presentation materials. In this way, the accuracy of the corrections can be improved by referring to related literature of the presentation materials. Some or all of the above-mentioned processing in the correction unit can be performed using, for example, AI, or can be performed without using AI. For example, the correction unit can input data of related literature of the presentation materials into AI and have the AI ​​improve the accuracy of the corrections.

[0107] The revision unit may take into account the market value of the presentation materials when making revisions. Market value includes, but is not limited to, sales forecasts and market research results. The revision unit may take into account the market value of the presentation materials when making revisions. For example, if the presentation materials have a high market value, the revision unit may make detailed revisions. Alternatively, if the presentation materials have a low market value, the revision unit may make simplified revisions. Furthermore, the revision unit may analyze the market value of the presentation materials and make optimal revisions. This allows the presentation materials to be revised efficiently by taking the market value of the presentation materials into consideration. Some or all of the above-described processing in the revision unit may be performed using, for example, AI, or may be performed without using AI. For example, the revision unit may input data on the market value of the presentation materials into AI and have the AI ​​execute the revision processing. === Hard Collateral 1-1 === Each of the multiple elements, including the collection unit, analysis unit, pointing out unit, and correction unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit can collect data on the executive's remarks and decision-making using the camera 42 and microphone 38B of the smart device 14. The collection unit can also collect data related to the executive's emails and work using the specific processing unit 290 of the data processing device 12. The analysis unit, realized, for example, by the specific processing unit 290 of the data processing device 12, analyzes the collected data and creates an individual avatar. The pointing out unit, realized, for example, by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12, analyzes presentation materials, predicts and presents points of criticism. The correction unit, realized, for example, by the specific processing unit 290 of the data processing device 12, corrects deficiencies in the materials based on the points of criticism. === Hard Collateral 1-2 === Each of the multiple elements, including the collection unit, analysis unit, indication unit, and correction unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit can collect data on the executive's remarks and decision-making using the camera 42 and microphone 238 of the smart glasses 214. The collection unit can also collect data related to the executive's emails and work using the specific processing unit 290 of the data processing device 12. The analysis unit, realized, for example, by the specific processing unit 290 of the data processing device 12, analyzes the collected data and creates an individual avatar. The indication unit, realized, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12, analyzes presentation materials, predicts and presents indications. The correction unit, realized, for example, by the specific processing unit 290 of the data processing device 12, corrects deficiencies in the materials based on the indications. === Hard Collateral 1-3 === Each of the multiple elements, including the collection unit, analysis unit, indication unit, and correction unit, described above, is realized, for example, by at least one of the headset terminal 314 and the data processing device 12. For example, the collection unit can collect data on the executive's remarks and decision-making using the camera 42 and microphone 238 of the headset terminal 314. The collection unit can also collect data related to the executive's emails and work using the specific processing unit 290 of the data processing device 12. The analysis unit, realized, for example, by the specific processing unit 290 of the data processing device 12, analyzes the collected data and creates an individual avatar. The indication unit, realized, for example, by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing device 12, analyzes presentation materials, predicts and presents indications. The correction unit, realized, for example, by the specific processing unit 290 of the data processing device 12, corrects deficiencies in the materials based on the indications. === Hard Collateral 1-4 === Each of the multiple elements, including the collection unit, analysis unit, pointing out unit, and correction unit, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit can collect data on the executive's remarks and decision-making using the camera 42 and microphone 238 of the robot 414. The collection unit can also collect data related to the executive's emails and work using the specific processing unit 290 of the data processing device 12. The analysis unit, realized, for example, by the specific processing unit 290 of the data processing device 12, analyzes the collected data and creates an individual avatar. The pointing out unit, realized, for example, by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12, analyzes presentation materials, predicts and presents points of criticism. The correction unit, realized, for example, by the specific processing unit 290 of the data processing device 12, corrects deficiencies in the materials based on the points of criticism.

[0108] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0109] The analysis unit estimates the stress level of a manager based on data on the manager's past statements and decision-making, and can temporarily suspend avatar generation if stress is high. For example, the analysis unit can analyze the manager's speech patterns and delays in decision-making when he or she felt stressed in the past and compare this with current data to estimate the manager's stress level. In addition, if stress is high, the analysis unit can temporarily suspend avatar generation, reducing the manager's burden. Furthermore, if stress is low, the analysis unit can resume avatar generation, allowing for efficient data collection. In this way, by adjusting avatar generation according to the manager's stress level, the manager's burden can be reduced and data can be collected efficiently.

[0110] The collection unit can analyze the past work history of executives and prioritize the collection of data related to specific projects. For example, executives can prioritize the collection of data on projects that were successful in the past and identify the factors that led to success in similar projects. They can also collect data on failed projects and take measures to avoid similar failures. Furthermore, they can prioritize the collection of data related to projects that executives are currently working on and support the progress of the projects. In this way, by prioritizing the collection of data related to specific projects based on the executives' past work history, the success rate of projects can be improved.

[0111] The analysis unit can estimate the emotions of the manager and adjust the avatar's speech based on the estimated emotions. For example, if the manager is feeling stressed, the avatar's speech can be made simpler, reducing the manager's burden. Also, if the manager is relaxed, the avatar's speech can be made more detailed, deepening the manager's understanding. Furthermore, if the manager is excited, the avatar's speech can be made calmer, stabilizing the manager's emotions. In this way, adjusting the avatar's speech according to the manager's emotions reduces the manager's burden and enables information to be provided efficiently.

[0112] When making comments on the content of presentation materials, the commenting unit can improve the accuracy of the comments by referring to past feedback from managers. For example, by analyzing feedback that managers have received in the past and making similar comments, the manager's understanding can be deepened. In addition, the content of the comments can be adjusted based on past feedback, and comments can be made to suit the needs of the manager. Furthermore, by referring to past feedback, the timing of comments can be adjusted, reducing the burden on the manager. In this way, by referring to past feedback from managers, the accuracy of comments can be improved and the burden on the manager can be reduced.

[0113] When revising presentation materials, the revision department can estimate the emotions of executives and set priorities for revisions based on the estimated emotions. For example, if an executive is feeling stressed, important revisions can be made first, reducing the executive's burden. Also, if an executive is relaxed, detailed revisions can be made first, improving the completeness of the materials. Furthermore, if an executive is in a hurry, revisions can be made quickly, saving the executive's time. Thus, by setting priorities for revisions according to the executive's emotions, materials can be revised efficiently.

[0114] The collection unit can analyze the social media activities of executives and collect related data. For example, the collection unit can collect related data based on information shared by executives on social media. The collection unit can also analyze the content of the executives' social media activities and collect related data. Furthermore, the collection unit can also collect related data by referring to the activities of the executives' friends on social media. In this way, by analyzing the social media activities of executives, related data can be collected efficiently.

[0115] The analysis unit can estimate the emotions of the manager and adjust the avatar generation speed based on the estimated emotions. For example, if the manager is in a hurry, the avatar generation speed can be increased. Also, if the manager is relaxed, the avatar generation speed can be decreased. Also, if the manager is excited, the avatar generation speed can be adjusted. In this way, avatars can be generated efficiently by adjusting the avatar generation speed according to the manager's emotions.

[0116] When providing feedback on the content of presentation materials, the feedback unit can adjust the content of the feedback according to the level of expertise of the executive. For example, if the executive has specialized knowledge, detailed feedback can be provided to deepen the executive's understanding. If the executive does not have specialized knowledge, brief feedback can be provided to reduce the executive's burden. Furthermore, the level of expertise of the executive can be analyzed and the content of the feedback can be optimized. This allows for efficient feedback by adjusting the content of the feedback according to the executive's level of expertise.

[0117] When revising presentation materials, the revision department can analyze the past revision history of the executives and select the optimal revision method. For example, the optimal revision method can be selected based on the past revision history of the executives. The revision method can also be optimized by analyzing the past revision history of the executives. Furthermore, the revision method can also be selected by referring to the past revision history of the executives. In this way, the optimal revision method can be selected by analyzing the past revision history of the executives.

[0118] When revising presentation materials, the revision department can estimate the emotions of executives and adjust the revision method based on the estimated emotions. For example, if an executive is feeling stressed, the department can suggest a simple revision method. If an executive is relaxed, the department can suggest a detailed revision method. If an executive is in a hurry, the department can suggest a quick revision method. In this way, documents can be revised efficiently by adjusting the revision method according to the executive's emotions.

[0119] The processing flow of the second embodiment will be briefly explained below.

[0120] Step 1: The collection department collects data on executive emails, transcripts, and decision-making. Executive emails include work-related emails, and transcripts include meeting minutes and audio recordings. Decision-making data includes the decision-making process and results. The collection department can collect a wide range of data related to executives' daily work, such as daily reports, meeting minutes, and project progress reports. Step 2: The analysis unit analyzes the data collected by the collection unit and creates individual avatars. The analysis unit uses text mining and natural language processing technology to analyze the data and learns the speech tendencies and decision-making patterns of executives. It also uses data mining technology to extract the characteristics of executives and reflect them in the avatars. Step 3: The avatar created by the analysis unit analyzes the presentation materials and predicts and presents suggestions. The suggestion unit uses machine learning algorithms and rule-based systems to analyze the contents of the presentation materials and presents suggestions such as "This part needs to be explained more specifically" or "The basis for this data should be made clearer." Step 4: The correction department corrects any deficiencies in the document based on the suggestions made by the suggestions department. The correction department can correct grammar, add or delete content, rehearse the presentation, and revise the document based on the suggestions. The correction department's processing may be performed using AI or without AI.

[0121] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0122] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0123] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0124] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0125] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0126] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0127] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0128] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0129] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0130] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0131] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0132] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0133] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0134] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0135] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0136] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0137] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0138] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0139] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0140] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0141] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0142] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0143] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0144] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0145] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0146] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0147] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0148] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0149] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0150] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0151] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0152] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0153] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0154] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0155] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0156] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0157] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0158] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0159] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0160] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0161] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0162] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0163] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0164] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0165] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0166] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0167] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0168] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0169] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0170] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0171] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0172] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0173] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0174] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0175] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0176] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0177] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0178] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0179] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0180] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0181] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0182] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0183] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0184] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0185] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0186] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0187] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0188] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0189] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0190] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0191] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0192] [Explanation of symbols]

[0193] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A collection department that collects emails, transcripts, and decision-making data from executives; an analysis unit that analyzes the data collected by the collection unit and creates an individual avatar; a commenting unit that uses the avatar created by the analysis unit to analyze the presentation materials and predict and present comments; A correction unit that corrects deficiencies in the material based on the indications presented by the indication unit.

2. The collecting unit Collect a wide range of data related to the daily work of executives The system of claim 1 .

3. The analysis unit Generate avatars that reflect the characteristics of executives based on collected data The system of claim 1 .

4. The indicating unit Anticipate and present comments about the contents of presentation materials The system of claim 1 .

5. The correction unit Correct any deficiencies in the materials based on the findings The system of claim 1 .

6. The indicating unit Use specific examples when presenting your findings The system of claim 1 .

7. The correction unit Rehearse your presentation and revise your materials based on feedback The system of claim 1 .

8. The collecting unit Estimate user emotions and determine the timing of data collection based on the estimated user emotions The system of claim 1 .

9. The collecting unit Analyze past work history of managers and select appropriate data collection methods The system of claim 1 .

10. The collecting unit When collecting data, filter it based on the executive's current projects and areas of interest. The system of claim 1 .

Images